net: stmmac: add per-queue TX & RX coalesce ethtool support

Extending the driver to support per-queue RX and TX coalesce settings in
order to support below commands:

To show per-queue coalesce setting:-
 $ ethtool --per-queue <DEVNAME> queue_mask <MASK> --show-coalesce

To set per-queue coalesce setting:-
 $ ethtool --per-queue <DEVNAME> queue_mask <MASK> --coalesce \
     [rx-usecs N] [rx-frames M] [tx-usecs P] [tx-frames Q]

Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index 2bac49b49f739233e5e9f94d2d8bc37d46162c76..90383abafa66acbba638c95e076b6a7fc7598b3e 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -255,7 +255,7 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr,
 }
 
 static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
-                                 u32 number_chan)
+                                 u32 queue)
 {
        writel(riwt, ioaddr + DMA_RX_WATCHDOG);
 }

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 62aa0e95beb709a65faefba7cafae6e9b6105ddc..8958778d16b773654fc826be31ef812d01014568 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -210,12 +210,9 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space)
                _dwmac4_dump_dma_regs(ioaddr, i, reg_space);
 }
 
-static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
+static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 queue)
 {
-       u32 chan;
-
-       for (chan = 0; chan < number_chan; chan++)
-               writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan));
+       writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(queue));
 }
 
 static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 77308c5c5d2947dc71b9d495f1b24202f909fd52..f2cab5b767320a1959a0d12fad3b3da4b8dd6718 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -441,12 +441,9 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
        dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3;
 }
 
-static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan)
+static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 queue)
 {
-       u32 i;
-
-       for (i = 0; i < nchan; i++)
-               writel(riwt & XGMAC_RWT, ioaddr + XGMAC_DMA_CH_Rx_WATCHDOG(i));
+       writel(riwt & XGMAC_RWT, ioaddr + XGMAC_DMA_CH_Rx_WATCHDOG(queue));
 }
 
 static void dwxgmac2_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 979ac9fca23c7bb1434a5c3f0717c035ee18f1c9..da9996a985f67f46772d8399218d5af4c49f9fd1 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -206,7 +206,7 @@ struct stmmac_dma_ops {
        void (*get_hw_feature)(void __iomem *ioaddr,
                               struct dma_features *dma_cap);
        /* Program the HW RX Watchdog */
-       void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan);
+       void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 queue);
        void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
        void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
        void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 10e8ae8e2d580bec74c78563acb9bef184143512..375c503d2df87bba8d67ce7f1878830c55f1a89b 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -147,9 +147,9 @@ struct stmmac_flow_entry {
 
 struct stmmac_priv {
        /* Frequently used values are kept adjacent for cache effect */
-       u32 tx_coal_frames;
-       u32 tx_coal_timer;
-       u32 rx_coal_frames;
+       u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
+       u32 tx_coal_timer[MTL_MAX_TX_QUEUES];
+       u32 rx_coal_frames[MTL_MAX_TX_QUEUES];
 
        int tx_coalesce;
        int hwts_tx_en;
@@ -160,7 +160,7 @@ struct stmmac_priv {
 
        unsigned int dma_buf_sz;
        unsigned int rx_copybreak;
-       u32 rx_riwt;
+       u32 rx_riwt[MTL_MAX_TX_QUEUES];
        int hwts_rx_en;
 
        void __iomem *ioaddr;

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index c5642985ef95cd55f7d686e5cb2a522fc700d349..a78d5b0686bf44a402751439d9a260f3d0ea1798 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -756,28 +756,75 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv)
        return (riwt * 256) / (clk / 1000000);
 }
 
-static int stmmac_get_coalesce(struct net_device *dev,
-                              struct ethtool_coalesce *ec)
+static int __stmmac_get_coalesce(struct net_device *dev,
+                                struct ethtool_coalesce *ec,
+                                int queue)
 {
        struct stmmac_priv *priv = netdev_priv(dev);
+       u32 max_cnt;
+       u32 rx_cnt;
+       u32 tx_cnt;
 
-       ec->tx_coalesce_usecs = priv->tx_coal_timer;
-       ec->tx_max_coalesced_frames = priv->tx_coal_frames;
+       rx_cnt = priv->plat->rx_queues_to_use;
+       tx_cnt = priv->plat->tx_queues_to_use;
+       max_cnt = max(rx_cnt, tx_cnt);
 
-       if (priv->use_riwt) {
-               ec->rx_max_coalesced_frames = priv->rx_coal_frames;
-               ec->rx_coalesce_usecs = stmmac_riwt2usec(priv->rx_riwt, priv);
+       if (queue < 0)
+               queue = 0;
+       else if (queue >= max_cnt)
+               return -EINVAL;
+
+       if (queue < tx_cnt) {
+               ec->tx_coalesce_usecs = priv->tx_coal_timer[queue];
+               ec->tx_max_coalesced_frames = priv->tx_coal_frames[queue];
+       } else {
+               ec->tx_coalesce_usecs = 0;
+               ec->tx_max_coalesced_frames = 0;
+       }
+
+       if (priv->use_riwt && queue < rx_cnt) {
+               ec->rx_max_coalesced_frames = priv->rx_coal_frames[queue];
+               ec->rx_coalesce_usecs = stmmac_riwt2usec(priv->rx_riwt[queue],
+                                                        priv);
+       } else {
+               ec->rx_max_coalesced_frames = 0;
+               ec->rx_coalesce_usecs = 0;
        }
 
        return 0;
 }
 
-static int stmmac_set_coalesce(struct net_device *dev,
+static int stmmac_get_coalesce(struct net_device *dev,
                               struct ethtool_coalesce *ec)
+{
+       return __stmmac_get_coalesce(dev, ec, -1);
+}
+
+static int stmmac_get_per_queue_coalesce(struct net_device *dev, u32 queue,
+                                        struct ethtool_coalesce *ec)
+{
+       return __stmmac_get_coalesce(dev, ec, queue);
+}
+
+static int __stmmac_set_coalesce(struct net_device *dev,
+                                struct ethtool_coalesce *ec,
+                                int queue)
 {
        struct stmmac_priv *priv = netdev_priv(dev);
-       u32 rx_cnt = priv->plat->rx_queues_to_use;
+       bool all_queues = false;
        unsigned int rx_riwt;
+       u32 max_cnt;
+       u32 rx_cnt;
+       u32 tx_cnt;
+
+       rx_cnt = priv->plat->rx_queues_to_use;
+       tx_cnt = priv->plat->tx_queues_to_use;
+       max_cnt = max(rx_cnt, tx_cnt);
+
+       if (queue < 0)
+               all_queues = true;
+       else if (queue >= max_cnt)
+               return -EINVAL;
 
        if (priv->use_riwt && (ec->rx_coalesce_usecs > 0)) {
                rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv);
@@ -785,8 +832,23 @@ static int stmmac_set_coalesce(struct net_device *dev,
                if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT))
                        return -EINVAL;
 
-               priv->rx_riwt = rx_riwt;
-               stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
+               if (all_queues) {
+                       int i;
+
+                       for (i = 0; i < rx_cnt; i++) {
+                               priv->rx_riwt[i] = rx_riwt;
+                               stmmac_rx_watchdog(priv, priv->ioaddr,
+                                                  rx_riwt, i);
+                               priv->rx_coal_frames[i] =
+                                       ec->rx_max_coalesced_frames;
+                       }
+               } else if (queue < rx_cnt) {
+                       priv->rx_riwt[queue] = rx_riwt;
+                       stmmac_rx_watchdog(priv, priv->ioaddr,
+                                          rx_riwt, queue);
+                       priv->rx_coal_frames[queue] =
+                               ec->rx_max_coalesced_frames;
+               }
        }
 
        if ((ec->tx_coalesce_usecs == 0) &&
@@ -797,13 +859,37 @@ static int stmmac_set_coalesce(struct net_device *dev,
            (ec->tx_max_coalesced_frames > STMMAC_TX_MAX_FRAMES))
                return -EINVAL;
 
-       /* Only copy relevant parameters, ignore all others. */
-       priv->tx_coal_frames = ec->tx_max_coalesced_frames;
-       priv->tx_coal_timer = ec->tx_coalesce_usecs;
-       priv->rx_coal_frames = ec->rx_max_coalesced_frames;
+       if (all_queues) {
+               int i;
+
+               for (i = 0; i < tx_cnt; i++) {
+                       priv->tx_coal_frames[i] =
+                               ec->tx_max_coalesced_frames;
+                       priv->tx_coal_timer[i] =
+                               ec->tx_coalesce_usecs;
+               }
+       } else if (queue < tx_cnt) {
+               priv->tx_coal_frames[queue] =
+                       ec->tx_max_coalesced_frames;
+               priv->tx_coal_timer[queue] =
+                       ec->tx_coalesce_usecs;
+       }
+
        return 0;
 }
 
+static int stmmac_set_coalesce(struct net_device *dev,
+                              struct ethtool_coalesce *ec)
+{
+       return __stmmac_set_coalesce(dev, ec, -1);
+}
+
+static int stmmac_set_per_queue_coalesce(struct net_device *dev, u32 queue,
+                                        struct ethtool_coalesce *ec)
+{
+       return __stmmac_set_coalesce(dev, ec, queue);
+}
+
 static int stmmac_get_rxnfc(struct net_device *dev,
                            struct ethtool_rxnfc *rxnfc, u32 *rule_locs)
 {
@@ -1001,6 +1087,8 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
        .get_ts_info = stmmac_get_ts_info,
        .get_coalesce = stmmac_get_coalesce,
        .set_coalesce = stmmac_set_coalesce,
+       .get_per_queue_coalesce = stmmac_get_per_queue_coalesce,
+       .set_per_queue_coalesce = stmmac_set_per_queue_coalesce,
        .get_channels = stmmac_get_channels,
        .set_channels = stmmac_set_channels,
        .get_tunable = stmmac_get_tunable,

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ddf54b8ad75d03b3cbd682ece8cda6ee152dbe30..1b34373a19181176400a85edcbe71419f0e4c299 100644 (file)
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2234,7 +2234,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 
        /* We still have pending packets, let's call for a new scheduling */
        if (tx_q->dirty_tx != tx_q->cur_tx)
-               hrtimer_start(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer),
+               hrtimer_start(&tx_q->txtimer,
+                             STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
                              HRTIMER_MODE_REL);
 
        __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
@@ -2519,7 +2520,8 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue)
 {
        struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 
-       hrtimer_start(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer),
+       hrtimer_start(&tx_q->txtimer,
+                     STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
                      HRTIMER_MODE_REL);
 }
 
@@ -2560,18 +2562,21 @@ static enum hrtimer_restart stmmac_tx_timer(struct hrtimer *t)
 static void stmmac_init_coalesce(struct stmmac_priv *priv)
 {
        u32 tx_channel_count = priv->plat->tx_queues_to_use;
+       u32 rx_channel_count = priv->plat->rx_queues_to_use;
        u32 chan;
 
-       priv->tx_coal_frames = STMMAC_TX_FRAMES;
-       priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
-       priv->rx_coal_frames = STMMAC_RX_FRAMES;
-
        for (chan = 0; chan < tx_channel_count; chan++) {
                struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
 
+               priv->tx_coal_frames[chan] = STMMAC_TX_FRAMES;
+               priv->tx_coal_timer[chan] = STMMAC_COAL_TX_TIMER;
+
                hrtimer_init(&tx_q->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
                tx_q->txtimer.function = stmmac_tx_timer;
        }
+
+       for (chan = 0; chan < rx_channel_count; chan++)
+               priv->rx_coal_frames[chan] = STMMAC_RX_FRAMES;
 }
 
 static void stmmac_set_rings_length(struct stmmac_priv *priv)
@@ -2876,10 +2881,15 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
                priv->tx_lpi_timer = eee_timer * 1000;
 
        if (priv->use_riwt) {
-               if (!priv->rx_riwt)
-                       priv->rx_riwt = DEF_DMA_RIWT;
+               u32 queue;
+
+               for (queue = 0; queue < rx_cnt; queue++) {
+                       if (!priv->rx_riwt[queue])
+                               priv->rx_riwt[queue] = DEF_DMA_RIWT;
 
-               ret = stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
+                       stmmac_rx_watchdog(priv, priv->ioaddr,
+                                          priv->rx_riwt[queue], queue);
+               }
        }
 
        if (priv->hw->pcs)
@@ -3378,11 +3388,12 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
        if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
                set_ic = true;
-       else if (!priv->tx_coal_frames)
+       else if (!priv->tx_coal_frames[queue])
                set_ic = false;
-       else if (tx_packets > priv->tx_coal_frames)
+       else if (tx_packets > priv->tx_coal_frames[queue])
                set_ic = true;
-       else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+       else if ((tx_q->tx_count_frames %
+                 priv->tx_coal_frames[queue]) < tx_packets)
                set_ic = true;
        else
                set_ic = false;
@@ -3607,11 +3618,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
        if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && priv->hwts_tx_en)
                set_ic = true;
-       else if (!priv->tx_coal_frames)
+       else if (!priv->tx_coal_frames[queue])
                set_ic = false;
-       else if (tx_packets > priv->tx_coal_frames)
+       else if (tx_packets > priv->tx_coal_frames[queue])
                set_ic = true;
-       else if ((tx_q->tx_count_frames % priv->tx_coal_frames) < tx_packets)
+       else if ((tx_q->tx_count_frames %
+                 priv->tx_coal_frames[queue]) < tx_packets)
                set_ic = true;
        else
                set_ic = false;
@@ -3810,11 +3822,11 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
                stmmac_refill_desc3(priv, rx_q, p);
 
                rx_q->rx_count_frames++;
-               rx_q->rx_count_frames += priv->rx_coal_frames;
-               if (rx_q->rx_count_frames > priv->rx_coal_frames)
+               rx_q->rx_count_frames += priv->rx_coal_frames[queue];
+               if (rx_q->rx_count_frames > priv->rx_coal_frames[queue])
                        rx_q->rx_count_frames = 0;
 
-               use_rx_wd = !priv->rx_coal_frames;
+               use_rx_wd = !priv->rx_coal_frames[queue];
                use_rx_wd |= rx_q->rx_count_frames > 0;
                if (!priv->use_riwt)
                        use_rx_wd = false;